In [36]:
import numpy as np
import pandas as pd
In [37]:
from sklearn.datasets import load_boston
In [38]:
boston = load_boston()
In [39]:
data = pd.DataFrame(boston.data)
In [40]:
data.head()
Out[40]:
In [41]:
data.columns = boston.feature_names
In [42]:
data['PRICE'] = boston.target
In [43]:
data.head(n=10)
Out[43]:
In [44]:
print(data.shape)
In [45]:
data.describe()
Out[45]:
In [46]:
data.info()
In [47]:
import seaborn as sns
In [48]:
sns.distplot(data.PRICE)
Out[48]:
In [49]:
sns.boxplot(data.PRICE)
Out[49]:
In [50]:
correlation = data.corr()
correlation.loc['PRICE']
Out[50]:
In [51]:
import matplotlib.pyplot as plt
In [52]:
import matplotlib.pyplot as plt
fig,axes = plt.subplots(figsize=(15,12))
sns.heatmap(correlation,square = True,annot = True)
Out[52]:
In [53]:
plt.figure(figsize = (20,5))
features = ['LSTAT','RM','PTRATIO']
for i, col in enumerate(features):
plt.subplot(1, len(features) , i+1)
x = data[col]
y = data.PRICE
plt.scatter(x, y, marker='o')
plt.title("Variation in House prices")
plt.xlabel(col)
plt.ylabel('"House prices in $1000"')
In [54]:
X = data.iloc[:,:-1]
y= data.PRICE
In [55]:
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=42)
In [56]:
mean = X_train.mean(axis=0)
std = X_train.std(axis=0)
X_train = (X_train - mean) / std
X_test = (X_test - mean) / std
In [57]:
from sklearn.linear_model import LinearRegression
In [58]:
regressor = LinearRegression()
In [59]:
regressor.fit(X_train,y_train)
Out[59]:
In [60]:
y_pred = regressor.predict(X_test)
In [61]:
from sklearn.metrics import mean_squared_error
rmse = (np.sqrt(mean_squared_error(y_test, y_pred)))
print(rmse)
In [62]:
from sklearn.metrics import r2_score
r2 = r2_score(y_test, y_pred)
print(r2)
In [63]:
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)
In [64]:
import keras
In [65]:
import tensorflow as tf
In [66]:
from keras.layers import Dense, Activation,Dropout
from keras.models import Sequential
In [67]:
model = Sequential()
model.add(Dense(128,activation = 'relu',input_dim =13))
model.add(Dense(64,activation = 'relu'))
In [68]:
model.add(Dense(32,activation = 'relu'))
model.add(Dense(16,activation = 'relu'))
model.add(Dense(1))
In [69]:
model.compile(optimizer = 'adam',loss ='mean_squared_error',metrics=['mae'])
In [70]:
!pip install ann_visualizer
!pip install graphviz
In [71]:
from ann_visualizer.visualize import ann_viz;
In [72]:
ann_viz(model, title="DEMO ANN");
In [73]:
history = model.fit(X_train, y_train, epochs=100, validation_split=0.05)
In [74]:
from plotly.subplots import make_subplots
import plotly.graph_objects as go
fig = go.Figure()
fig.add_trace(go.Scattergl(y=history.history['loss'],
name='Train'))
fig.add_trace(go.Scattergl(y=history.history['val_loss'],
name='Valid'))
fig.update_layout(height=500, width=700,
xaxis_title='Epoch',
yaxis_title='Loss')
fig.show()
In [75]:
fig = go.Figure()
fig.add_trace(go.Scattergl(y=history.history['mae'],
name='Train'))
fig.add_trace(go.Scattergl(y=history.history['val_mae'],
name='Valid'))
fig.update_layout(height=500, width=700,
xaxis_title='Epoch',
yaxis_title='Mean Absolute Error')
fig.show()
In [76]:
y_pred = model.predict(X_test)
mse_nn, mae_nn = model.evaluate(X_test, y_test)
print('Mean squared error on test data: ', mse_nn)
print('Mean absolute error on test data: ', mae_nn)
In [77]:
from sklearn.metrics import mean_absolute_error
lr_model = LinearRegression()
lr_model.fit(X_train, y_train)
Out[77]:
In [78]:
y_pred_lr = lr_model.predict(X_test)
mse_lr = mean_squared_error(y_test, y_pred_lr)
mae_lr = mean_absolute_error(y_test, y_pred_lr)
print('Mean squared error on test data: ', mse_lr)
print('Mean absolute error on test data: ', mae_lr)
from sklearn.metrics import r2_score
r2 = r2_score(y_test, y_pred)
print(r2)
In [79]:
from sklearn.metrics import mean_squared_error
rmse = (np.sqrt(mean_squared_error(y_test, y_pred)))
print(rmse)
In [80]:
import sklearn
new_data = sklearn.preprocessing.StandardScaler().fit_transform(([[0.1, 10.0,
5.0, 0, 0.4, 6.0, 50, 6.0, 1, 400, 20, 300, 10]]))
prediction = model.predict(new_data)
print("Predicted house price:", prediction)
In [ ]: